Investigation the Cocracking of C4-Cut Raffinate and Naphtha in Industrial Cracker-Application of the Artificial Neural Network (ANN) & Mathematical Modeling

A. Niaei, D. Salari, J. Towfighi, and R. Nabavi (Iran)


Modeling, Cocracking, C4cut raffinate, Artificial neural networks


With the help of a complete reaction network, the cocracking of C4 cut raffinate and naphtha feed was investigated. The presence of higher concentration of butadiene in C4 cut affects the ethylene and propylene yields, amounts of coke formation and operating run length. Artificial neural networks (ANNs) are a promising alternative modeling technique. They are computer-based systems that are designed to simulate the learning process of neurons in the human brain. The optimum structure of neural network was determined by a trial and error method. Different structures were tried with several neurons in the hidden layer. Quite good agreement was found between model results and experimental data. A comparison between the results of mathematical model and designed ANN was also conducted and the relative absolute error was calculated.

Important Links:

Go Back